{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HPS53PAHWFCSURO5SXPTIA4FL2","short_pith_number":"pith:HPS53PAH","schema_version":"1.0","canonical_sha256":"3be5ddbc07b1452a45dd95df3403855eafea5d0ddfeb9351918bc3e760edb7c4","source":{"kind":"arxiv","id":"1809.10121","version":2},"attestation_state":"computed","paper":{"title":"Safely Learning to Control the Constrained Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Benjamin Recht, Nikolai Matni, Sarah Dean, Stephen Tu","submitted_at":"2018-09-26T17:04:59Z","abstract_excerpt":"We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of state and input constraints. This framework involves a novel method for synthesizing robust constraint-satisfying feedback controllers, leveraging newly developed tools from system level synthesis. We connect statistical results with cost sub-optimality bounds to give non-asymptoti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1809.10121","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-26T17:04:59Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fec3d244e5fe259ae226585b536398cd7a18fc33436c58270a18cb8da8e416e7","abstract_canon_sha256":"94301c81abf3fb4413bea2f15a1d958b71259921967bc9e3c4798d1f3fa3a512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:17.848296Z","signature_b64":"XJw1HNdrZgeQrQ1RXhwZvyrnfyaA3IN775R+skluw5QviB5Qiexxywb+Pcbr15/phOYAlYKrAHfD8UjqXbMrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3be5ddbc07b1452a45dd95df3403855eafea5d0ddfeb9351918bc3e760edb7c4","last_reissued_at":"2026-05-17T23:41:17.847684Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:17.847684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safely Learning to Control the Constrained Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Benjamin Recht, Nikolai Matni, Sarah Dean, Stephen Tu","submitted_at":"2018-09-26T17:04:59Z","abstract_excerpt":"We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of state and input constraints. This framework involves a novel method for synthesizing robust constraint-satisfying feedback controllers, leveraging newly developed tools from system level synthesis. We connect statistical results with cost sub-optimality bounds to give non-asymptoti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.10121","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.10121","created_at":"2026-05-17T23:41:17.847780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.10121v2","created_at":"2026-05-17T23:41:17.847780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.10121","created_at":"2026-05-17T23:41:17.847780+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPS53PAHWFCS","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPS53PAHWFCSURO5","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPS53PAH","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12189","citing_title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2","json":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2.json","graph_json":"https://pith.science/api/pith-number/HPS53PAHWFCSURO5SXPTIA4FL2/graph.json","events_json":"https://pith.science/api/pith-number/HPS53PAHWFCSURO5SXPTIA4FL2/events.json","paper":"https://pith.science/paper/HPS53PAH"},"agent_actions":{"view_html":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2","download_json":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2.json","view_paper":"https://pith.science/paper/HPS53PAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.10121&json=true","fetch_graph":"https://pith.science/api/pith-number/HPS53PAHWFCSURO5SXPTIA4FL2/graph.json","fetch_events":"https://pith.science/api/pith-number/HPS53PAHWFCSURO5SXPTIA4FL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2/action/storage_attestation","attest_author":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2/action/author_attestation","sign_citation":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2/action/citation_signature","submit_replication":"https://pith.science/pith/HPS53PAHWFCSURO5SXPTIA4FL2/action/replication_record"}},"created_at":"2026-05-17T23:41:17.847780+00:00","updated_at":"2026-05-17T23:41:17.847780+00:00"}